ABSTRACT
Objective:To construct an intelligent foreign bodies detection model based on Faster R-convolutional neural network in posterior-anterior chest X-ray and evaluate the performance of the model.Methods:Totally 5 567 adult posterior-anterior DR chest radiographs from Zhejiang Provincial People′s Hospital and Chun′an County People′s Hospital from June 2019 to March 2020, with 4 247 foreign body-containing chest radiographs were analyzed retrospectively. All data were randomly divided into training set (2 911 foreign body-containing), validation set ( n=1 456, 733 foreign body-containing, 723 free of foreign body) and testing set ( n=1 200, 603 foreign body-containing, 597 free of foreign body). The reference gold standard was set as the results of each chest radiography with foreign body annotated by two radiology residents and reviewed and corrected by a senior radiographer. The receiver operating characteristic (ROC) curve and the area under the curve were used to analyze the efficiency of the deep learning model to distinguish the presence or absence of foreign bodies on chest radiography in the testing set. The precision-recall curve and mean precision (mAP) were used to analyze the stability of the model at different levels. Finally, the influence of different locations, patient gender, and patient age on the foreign body recall of the deep learning model were analyzed. Results:In the testing set, the sensitivity of the deep learning model in diagnosing whether chest radiograph contained foreign bodies was 93.2%(562/603), the specificity was 92.6%(553/597), and the F1 score was 0.94. The area under the ROC curve was 0.97, and the mAP value was 0.69. For foreign bodies in different locations, the recall rates of foreign bodies in lung field and outside lung field were 91.2% (674/739) and 89.0% (1 411/1 585), respectively. For different genders, the recall rates for male and female foreign body detection were 87.3% (337/386) and 90.0%(1 745/1 938), respectively. For different age ranges, the recall rate of foreign body detection was 92.5% (1 041/1 126) for 18-38 years old, 89.7%(505/563) for 39-58 years old, 83.5%(335/401) for 59-78 years old and 85.9% (201/234) for patients ≥79 years old.Conclusion:The constructed deep learning-based foreign body detection model for adult posterior-anterior chest X-ray provides high sensitivity and stability, which can identify foreign bodies in chest radiography quickly and accurately.
ABSTRACT
Objective: To investigate the mechanism of moxibustion in the treatment of diarrhea-predominant irritable bowel syndrome (IBS-D), by observing the effects of moxibustion at Tianshu (ST25) and Shangjuxu (ST37) on microRNA-133b (miRNA-133b), pituitary homeobox family factor 3 (Pitx3)/tyrosine hydroxylase (TH), and neurotransmitters in the brain tissue of IBS-D rats. Methods: Healthy Sprague-Dawley rats were randomly divided into a normal group, a model group, a moxibustion group, and a Western medicine group, with 12 rats in each group. Except for the normal group, the IBS-D rat model was established by mother-offspring separation and acetic acid enema combined with restraint stress stimulation in all the other groups. No intervention was performed in the normal and model groups. Mild moxibustion was applied to both Tianshu (ST25) and Shangjuxu (ST37) in the moxibustion group. Rifaximin was given by gavage in the Western medicine group. The physical status of rats in each group was observed at different periods. After the intervention, hematoxylin- eosin staining was performed to observe the histopathological morphology of rat colon; enzyme-linked immunosorbent assay was used to measure the levels of dopamine (DA), noradrenaline (NE), and 5-hydroxytryptamine (5-HT) in plasma, colon, and midbrain tissue of rats; the relative expression levels of miRNA-133b, Pitx3 mRNA, and TH mRNA in the midbrain tissue were measured by real-time fluorescence quantitative polymerase chain reaction, and the relative expression levels of Pitx3 and TH proteins in the midbrain tissue were measured by Western blotting and immunofluorescence. Results: The body weights of rats among groups and at different time points were statistically different (P<0.01). The body weight of the normal group was higher than that of the other groups over time (P<0.01). After modeling, the minimum volume threshold of abdominal withdrawal reflex (AWR) was significantly lower (P<0.01) and the loose stool rate was significantly higher (P<0.01) in the model, moxibustion, and Western medicine groups compared with the normal group; the miRNA-133b expression in the midbrain tissue was significantly lower (P<0.01), the expression levels of Pitx3 and TH in the midbrain tissue were significantly higher (P<0.01), and the levels of DA, NE, and 5-HT in plasma, colon and midbrain tissue were significantly higher (P<0.01). After the intervention, the minimum volume threshold of AWR was significantly higher (P<0.01), the loose stool rate was significantly lower (P<0.01), the miRNA-133b expression was significantly increased (P<0.01 or P<0.05) and the expression levels of Pitx3 and TH were significantly decreased (P<0.01) in the midbrain tissue, the levels of DA, NE, and 5-HT in plasma, colon, and midbrain tissue were significantly reduced (P<0.01) in the moxibustion and Western medicine groups compared with the model group; the levels of 5-HT in the colon and midbrain tissue of the moxibustion group were significantly lower than those in the Western medicine group (P<0.05), and there was no statistical difference compared with the remaining groups (P>0.05). Linear correlation analysis showed that miRNA-133b was negatively correlated with Pitx3 (r<0, P<0.01); Pitx3 with TH, TH with DA, and NE with 5-HT were positively correlated (r>0, P<0.01).Conclusion: Moxibustion at Tianshu (ST25) and Shangjuxu (ST37) improves diarrhea symptoms and visceral hypersensitivity in IBS-D rats. The mechanism may be related to up-regulating miRNA-133b, inhibiting Pitx3/TH, and reducing neurotransmitter expression levels in the midbrain tissue.